© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 74647
    Prev
    Next
    INDEX
    Explanations

    copyright and legal use

    np_max-act · gemini-2.0-flash

    tokens that appear in questions or explanations about licensing, copyright, and legal permission for using creative works.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    쌘
    -0.08
    ousy
    -0.08
    /St
    -0.07
     gravy
    -0.07
    .IsTrue
    -0.07
     trot
    -0.07
    _Of
    -0.07
    名列前茅
    -0.07
     Sanford
    -0.07
    IBILITY
    -0.07
    POSITIVE LOGITS
    component
    0.07
     faith
    0.07
    到场
    0.07
    Accounts
    0.07
     Kub
    0.07
    ca
    0.07
    Publish
    0.07
    examples
    0.07
    Gu
    0.06
    셢
    0.06
    Activations Density 0.096%

    No Known Activations